{"id":"https://openalex.org/W2127881761","doi":"https://doi.org/10.1109/tpds.2002.1058095","title":"Recursive array layouts and fast matrix multiplication","display_name":"Recursive array layouts and fast matrix multiplication","publication_year":2002,"publication_date":"2002-11-01","ids":{"openalex":"https://openalex.org/W2127881761","doi":"https://doi.org/10.1109/tpds.2002.1058095","mag":"2127881761"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2002.1058095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2002.1058095","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101930377","display_name":"Siddhartha Chatterjee","orcid":"https://orcid.org/0000-0003-3100-7793"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"S. Chatterjee","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","[IBM Thomas J. Watson Research Center, Yorktown Heights, NY , USA]"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM Thomas J. Watson Research Center, Yorktown Heights, NY , USA]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029011254","display_name":"Alvin R. Lebeck","orcid":"https://orcid.org/0000-0003-1893-5464"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A.R. Lebeck","raw_affiliation_strings":["Department of Computer Science, Duke University, Durham, USA","Department of Computer Science Duke University, Durham, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Duke University, Durham, USA","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Department of Computer Science Duke University, Durham, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078009583","display_name":"Praveen K. Patnala","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P.K. Patnala","raw_affiliation_strings":["Department of Computer Science, Duke University, Durham, NC, USA","Dept. of Comput. Sci., Duke Univ., Durham, NC, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Duke Univ., Durham, NC, USA#TAB#","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069139257","display_name":"Mithuna Thottethodi","orcid":"https://orcid.org/0000-0003-4164-4542"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M. Thottethodi","raw_affiliation_strings":["Nexsi Corporation, San Jose, CA, USA","[Nexsi Corporation, San Jose, CA, USA]"],"affiliations":[{"raw_affiliation_string":"Nexsi Corporation, San Jose, CA, USA","institution_ids":[]},{"raw_affiliation_string":"[Nexsi Corporation, San Jose, CA, USA]","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101930377"],"corresponding_institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":2.877,"has_fulltext":false,"cited_by_count":93,"citation_normalized_percentile":{"value":0.91494816,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"13","issue":"11","first_page":"1105","last_page":"1123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/strassen-algorithm","display_name":"Strassen algorithm","score":0.9692409038543701},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.7757357358932495},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7727563381195068},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6181845664978027},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6080436706542969},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5373477339744568},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5140088796615601},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4734059274196625},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4609648883342743},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.43497616052627563},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18133017420768738}],"concepts":[{"id":"https://openalex.org/C39096654","wikidata":"https://www.wikidata.org/wiki/Q728507","display_name":"Strassen algorithm","level":4,"score":0.9692409038543701},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.7757357358932495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7727563381195068},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6181845664978027},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6080436706542969},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5373477339744568},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5140088796615601},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4734059274196625},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4609648883342743},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.43497616052627563},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18133017420768738},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/tpds.2002.1058095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2002.1058095","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:ADA440384","is_oa":false,"landing_page_url":"http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA440384","pdf_url":null,"source":{"id":"https://openalex.org/S4406923043","display_name":"Defense Technical Information Center (DTIC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"DTIC AND NTIS","raw_type":"Text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.32.8592","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.32.8592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.cs.unc.edu/pub/users/sc/papers/tpds-strassen.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.43.1510","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.43.1510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.cs.unc.edu/pub/users/sc/papers/toms-matmul.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.8.8694","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.8.8694","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.duke.edu/~alvy/papers/matrix-tpds.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.915.8757","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.915.8757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dtic.mil/get-tr-doc/pdf?AD%3DADA440384%26Location%3DU2%26doc%3DGetTRDoc.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W171476335","https://openalex.org/W1521571223","https://openalex.org/W1522470213","https://openalex.org/W1543026697","https://openalex.org/W1573851230","https://openalex.org/W1577415865","https://openalex.org/W1803362547","https://openalex.org/W1805609323","https://openalex.org/W1850405760","https://openalex.org/W1972209410","https://openalex.org/W1973122629","https://openalex.org/W1977256916","https://openalex.org/W1979928925","https://openalex.org/W1998513737","https://openalex.org/W2002257715","https://openalex.org/W2004916460","https://openalex.org/W2007768252","https://openalex.org/W2008117760","https://openalex.org/W2015190123","https://openalex.org/W2016358147","https://openalex.org/W2020214444","https://openalex.org/W2020804487","https://openalex.org/W2024804689","https://openalex.org/W2026237859","https://openalex.org/W2032052535","https://openalex.org/W2032401773","https://openalex.org/W2035476608","https://openalex.org/W2038339443","https://openalex.org/W2040832766","https://openalex.org/W2040879131","https://openalex.org/W2050487400","https://openalex.org/W2056971515","https://openalex.org/W2061291998","https://openalex.org/W2063249715","https://openalex.org/W2072605585","https://openalex.org/W2096070062","https://openalex.org/W2098220211","https://openalex.org/W2098379190","https://openalex.org/W2104861744","https://openalex.org/W2111709480","https://openalex.org/W2119609467","https://openalex.org/W2131541431","https://openalex.org/W2133927618","https://openalex.org/W2135653967","https://openalex.org/W2136770272","https://openalex.org/W2138665068","https://openalex.org/W2143291413","https://openalex.org/W2154114943","https://openalex.org/W2159772324","https://openalex.org/W2162169073","https://openalex.org/W2167296849","https://openalex.org/W2168846776","https://openalex.org/W2244841219","https://openalex.org/W2498568530","https://openalex.org/W2769954494","https://openalex.org/W3022909171","https://openalex.org/W3136479147","https://openalex.org/W3139307873","https://openalex.org/W3145739035","https://openalex.org/W4206525843","https://openalex.org/W4210551159","https://openalex.org/W4239400817","https://openalex.org/W4240774490","https://openalex.org/W4243796884","https://openalex.org/W4246962530","https://openalex.org/W4247459116","https://openalex.org/W4249066449","https://openalex.org/W4251806996","https://openalex.org/W4255978229","https://openalex.org/W4255982026","https://openalex.org/W6606937033","https://openalex.org/W6634207108","https://openalex.org/W6634673738","https://openalex.org/W6645002406","https://openalex.org/W6658575193","https://openalex.org/W6793026607"],"related_works":["https://openalex.org/W1829171354","https://openalex.org/W1974407206","https://openalex.org/W2004916460","https://openalex.org/W2962985479","https://openalex.org/W2020777648","https://openalex.org/W2772956802","https://openalex.org/W2039853057","https://openalex.org/W1523285705","https://openalex.org/W2069906535","https://openalex.org/W2041189380"],"abstract_inverted_index":{"The":[0],"performance":[1,37,53,133],"of":[2,8,47,83,101,148,159,179,202],"both":[3],"serial":[4],"and":[5,20,54,71,78,86,113,131,137,184],"parallel":[6],"implementations":[7],"matrix":[9,39,61,76,150,166],"multiplication":[10,62,77],"is":[11,63,122,152,186],"highly":[12],"sensitive":[13],"to":[14,30,51,65,124,127,145,154,163],"memory":[15,35,129],"system":[16,36],"behavior.":[17],"False":[18],"sharing":[19],"cache":[21],"conflicts":[22],"cause":[23],"traditional":[24,93],"column-major":[25],"or":[26],"row-major":[27],"array":[28,49,69],"layouts":[29,50,70,90,94,161,174],"incur":[31],"high":[32],"variability":[33],"in":[34,194],"as":[38],"size":[40],"varies.":[41],"This":[42],"paper":[43],"investigates":[44],"the":[45,79,104,141,146,198],"use":[46],"recursive":[48,60,68,73,89,142,160,173],"improve":[52,132],"reduce":[55],"variability.":[56],"Previous":[57],"work":[58],"on":[59],"extended":[64],"examine":[66],"several":[67],"three":[72],"algorithms:":[74],"standard":[75,105],"more":[80],"complex":[81],"algorithms":[82],"Strassen":[84],"(1969)":[85],"Winograd.":[87],"While":[88],"significantly":[91],"outperform":[92],"(reducing":[95],"execution":[96],"times":[97],"by":[98],"a":[99,117,157],"factor":[100],"1.2-2.5)":[102],"for":[103,111,197],"algorithm,":[106],"they":[107],"offer":[108],"little":[109],"improvement":[110],"Strassen's":[112],"Winograd's":[114],"algorithms.":[115],"For":[116],"purely":[118],"sequential":[119],"implementation,":[120],"it":[121,185],"possible":[123],"reorder":[125],"computation":[126,181],"conserve":[128],"space":[130],"between":[134],"10":[135],"percent":[136],"20":[138],"percent.":[139],"Carrying":[140],"layout":[143],"down":[144,162],"level":[147],"individual":[149],"elements":[151],"shown":[153,187],"be":[155,192],"counterproductive;":[156],"combination":[158],"canonically":[164],"ordered":[165],"tiles":[167],"instead":[168],"yields":[169],"higher":[170],"performance.":[171],"Five":[172],"with":[175],"successively":[176],"increasing":[177],"complexity":[178],"address":[180],"are":[182],"evaluated":[183],"that":[188],"addressing":[189],"overheads":[190],"can":[191],"kept":[193],"control":[195],"even":[196],"most":[199],"computationally":[200],"demanding":[201],"these":[203],"layouts.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":8}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}